Open-Domain Frame Semantic Parsing Using Transformers
This work addresses the complex problem of frame semantic parsing for natural language processing researchers, offering incremental improvements over existing methods.
The paper tackled frame semantic parsing by exploring multi-task learning of all subtasks with transformer-based models, achieving state-of-the-art performance on FrameNet 1.7 and PropBank SRL parsing benchmarks with improved accuracy scores.
Frame semantic parsing is a complex problem which includes multiple underlying subtasks. Recent approaches have employed joint learning of subtasks (such as predicate and argument detection), and multi-task learning of related tasks (such as syntactic and semantic parsing). In this paper, we explore multi-task learning of all subtasks with transformer-based models. We show that a purely generative encoder-decoder architecture handily beats the previous state of the art in FrameNet 1.7 parsing, and that a mixed decoding multi-task approach achieves even better performance. Finally, we show that the multi-task model also outperforms recent state of the art systems for PropBank SRL parsing on the CoNLL 2012 benchmark.